© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29636
    Prev
    Next
    INDEX
    Explanations

    quantities, measurements, or numerical data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nings
    -0.07
    oldt
    -0.07
    eid
    -0.07
    ìĽĶ
    -0.07
    umbed
    -0.07
    éĺħ读次æķ°
    -0.07
     æľĪ
    -0.07
    zÃŃ
    -0.07
    Û°Û°
    -0.07
    undred
    -0.07
    POSITIVE LOGITS
    ipping
    0.07
    otechnology
    0.06
     Fus
    0.06
    wide
    0.06
    shire
    0.06
     Patrick
    0.06
     hip
    0.06
    th
    0.05
    ÏĮ
    0.05
    kontakte
    0.05
    Activations Density 0.136%

    No Known Activations